This is my undergraduate honors thesis and the cumulation of my Computer Science education at North Central College. This project came into existence from a desire to use Wikipedia data as a corpus for Natural Language Processing. Since indexing textbooks is an expensive problem, it made sense to attempt to use the data for social good.
To download a copy, check out the "releases" tab on the top of the GitHub project page and select the latest version. I hope you find as much value in reading it as I did in writing it.